DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input

by   Zihao Bo, et al.
Tsinghua University

We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs. Our model is called DenseAttentionSeg, which contains a dense attention mechanism to fuse information in different scales and improves the results quality with skip-connections. Besides, we introduce a contour loss in model training, which helps to generate accurate hand and object boundaries. Finally, we propose and will release our InterSegHands dataset, a fine-scale hand segmentation dataset containing about 52k depth maps of hand-object interactions. Our experiments evaluate the effectiveness of our techniques and datasets, and indicate that our method outperforms the current state-of-the-art deep segmentation methods on interaction segmentation.


page 1

page 3

page 4

page 7

page 8

page 9


Interacting Hand-Object Pose Estimation via Dense Mutual Attention

3D hand-object pose estimation is the key to the success of many compute...

Hand Segmentation for Hand-Object Interaction from Depth map

Hand-object interaction is important for many applications such as augme...

Unknown Object Segmentation from Stereo Images

Although instance-aware perception is a key prerequisite for many autono...

Analysis of Hand Segmentation in the Wild

A large number of works in egocentric vision have concentrated on action...

Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance

Pseudo depth maps are depth map predicitions which are used as ground tr...

Probabilistic 3D Multilabel Real-time Mapping for Multi-object Manipulation

Probabilistic 3D map has been applied to object segmentation with multip...

Please sign up or login with your details

Forgot password? Click here to reset